Object Recognition. So what does object recognition involve?

Slides:



Advertisements
Similar presentations
Distinctive Image Features from Scale-Invariant Keypoints
Advertisements

Joint Face Alignment The Recognition Pipeline
Distinctive Image Features from Scale-Invariant Keypoints David Lowe.
Evaluating Color Descriptors for Object and Scene Recognition Koen E.A. van de Sande, Student Member, IEEE, Theo Gevers, Member, IEEE, and Cees G.M. Snoek,
Computer Vision for Human-Computer InteractionResearch Group, Universität Karlsruhe (TH) cv:hci Dr. Edgar Seemann 1 Computer Vision: Histograms of Oriented.
Complex Feature Recognition: A Bayesian Approach for Learning to Recognize Objects by Paul A. Viola Presented By: Emrah Ceyhan Divin Proothi Sherwin Shaidee.
Based on slides created by Edward Angel
1 Angel: Interactive Computer Graphics 5E © Addison-Wesley 2009 Shading I.
Image alignment Image from
Instructor: Mircea Nicolescu Lecture 13 CS 485 / 685 Computer Vision.
Object Recognition. So what does object recognition involve?
Fast High-Dimensional Feature Matching for Object Recognition David Lowe Computer Science Department University of British Columbia.
University of British Columbia CPSC 314 Computer Graphics Jan-Apr 2008 Tamara Munzner Lighting/Shading II Week.
Robust and large-scale alignment Image from
1 Image Recognition - I. Global appearance patterns Slides by K. Grauman, B. Leibe.
A Study of Approaches for Object Recognition
Object Recognition. So what does object recognition involve?
Automatic Image Alignment (feature-based) : Computational Photography Alexei Efros, CMU, Fall 2005 with a lot of slides stolen from Steve Seitz and.
Distinctive Image Feature from Scale-Invariant KeyPoints
Distinctive image features from scale-invariant keypoints. David G. Lowe, Int. Journal of Computer Vision, 60, 2 (2004), pp Presented by: Shalomi.
University of British Columbia CPSC 314 Computer Graphics Jan-Apr 2005 Tamara Munzner Lighting and Shading Week.
Scale Invariant Feature Transform (SIFT)
Visual Object Recognition Rob Fergus Courant Institute, New York University
Object recognition under varying illumination. Lighting changes objects appearance.
Using Image Priors in Maximum Margin Classifiers Tali Brayer Margarita Osadchy Daniel Keren.
Anti-Faces for Detection Daniel Keren Rita Osadchy Haifa University Craig Gotsman Technion Journal Version:
1 Angel: Interactive Computer Graphics 4E © Addison-Wesley 2005 Shading I Ed Angel Professor of Computer Science, Electrical and Computer Engineering,
Lighting affects appearance. Light Source emits photons Photons travel in a straight line When they hit an object they: bounce off in a new direction.
Face Detection and Recognition
CS 480/680 Computer Graphics Shading I Dr. Frederick C Harris, Jr.
CS 485/685 Computer Vision Face Recognition Using Principal Components Analysis (PCA) M. Turk, A. Pentland, "Eigenfaces for Recognition", Journal of Cognitive.
Face Recognition Using Neural Networks Presented By: Hadis Mohseni Leila Taghavi Atefeh Mirsafian.
CS 445 / 645: Introductory Computer Graphics
Distinctive Image Features from Scale-Invariant Keypoints By David G. Lowe, University of British Columbia Presented by: Tim Havinga, Joël van Neerbos.
Computer vision.
Face Recognition and Feature Subspaces
Face Recognition and Feature Subspaces
Internet-scale Imagery for Graphics and Vision James Hays cs195g Computational Photography Brown University, Spring 2010.
EADS DS / SDC LTIS Page 1 7 th CNES/DLR Workshop on Information Extraction and Scene Understanding for Meter Resolution Image – 29/03/07 - Oberpfaffenhofen.
Window-based models for generic object detection Mei-Chen Yeh 04/24/2012.
Face Recognition: An Introduction
MSRI workshop, January 2005 Object Recognition Collected databases of objects on uniform background (no occlusions, no clutter) Mostly focus on viewpoint.
Lecture 7: Features Part 2 CS4670/5670: Computer Vision Noah Snavely.
Visual Categorization With Bags of Keypoints Original Authors: G. Csurka, C.R. Dance, L. Fan, J. Willamowski, C. Bray ECCV Workshop on Statistical Learning.
11/26/2015 Copyright G.D. Hager Class 2 - Schedule 1.Optical Illusions 2.Lecture on Object Recognition 3.Group Work 4.Sports Videos 5.Short Lecture on.
Jack Pinches INFO410 & INFO350 S INFORMATION SCIENCE Computer Vision I.
Li Fei-Fei, UIUC Rob Fergus, MIT Antonio Torralba, MIT Recognizing and Learning Object Categories ICCV 2005 Beijing, Short Course, Oct 15.
A Tutorial on using SIFT Presented by Jimmy Huff (Slightly modified by Josiah Yoder for Winter )
Distinctive Image Features from Scale-Invariant Keypoints
1Ellen L. Walker 3D Vision Why? The world is 3D Not all useful information is readily available in 2D Why so hard? “Inverse problem”: one image = many.
776 Computer Vision Jan-Michael Frahm Spring 2012.
Face Recognition and Feature Subspaces Devi Parikh Virginia Tech 11/05/15 Slides borrowed from Derek Hoiem, who borrowed some slides from Lana Lazebnik,
Finding Clusters within a Class to Improve Classification Accuracy Literature Survey Yong Jae Lee 3/6/08.
Distinctive Image Features from Scale-Invariant Keypoints Presenter :JIA-HONG,DONG Advisor : Yen- Ting, Chen 1 David G. Lowe International Journal of Computer.
Blob detection.
Computer Graphics: Illumination
776 Computer Vision Jan-Michael Frahm Spring 2012.
SIFT Scale-Invariant Feature Transform David Lowe
Lecture 07 13/12/2011 Shai Avidan הבהרה: החומר המחייב הוא החומר הנלמד בכיתה ולא זה המופיע / לא מופיע במצגת.
Distinctive Image Features from Scale-Invariant Keypoints
Traffic Sign Recognition Using Discriminative Local Features Andrzej Ruta, Yongmin Li, Xiaohui Liu School of Information Systems, Computing and Mathematics.
Feature description and matching
Object detection as supervised classification
Outline Peter N. Belhumeur, Joao P. Hespanha, and David J. Kriegman, “Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection,”
CAP 5415 Computer Vision Fall 2012 Dr. Mubarak Shah Lecture-5
Aim of the project Take your image Submit it to the search engine
Brief Review of Recognition + Context
Announcements Project 4 out today Project 2 winners help session today
Feature descriptors and matching
Anti-Faces for Detection
Presentation transcript:

Object Recognition

So what does object recognition involve?

Verification: is that a bus?

Detection: are there cars?

Identification: is that a picture of Mao?

Object categorization sky building flag wall banner bus cars bus face street lamp

Challenges 1: view point variation Michelangelo

Challenges 2: illumination slide credit: S. Ullman

Challenges 3: occlusion Magritte, 1957

Challenges 4: scale

Challenges 5: deformation Xu, Beihong 1943

Challenges 7: intra-class variation

Two main approaches Part-based Global sub-window

Global Approaches x1x1 x2x2 x3x3 Vectors in high- dimensional space Aligned images

x1x1 x2x2 x3x3 Vectors in high-dimensional space Global Approaches Training Involves some dimensionality reduction Detector

–Scale / position range to search over Detection

–Scale / position range to search over

Detection –Scale / position range to search over

Detection –Combine detection over space and scale.

PROJECT 1

Turk and Pentland, 1991 Belhumeur et al Schneiderman et al Viola and Jones, 2000 Keren et al Osadchy et al Amit and Geman, 1999 LeCun et al Belongie and Malik, 2002 Schneiderman et al Argawal and Roth, 2002 Poggio et al. 1993

Object Detection Problem: Locate instances of object category in a given image. Asymmetric classification problem! BackgroundObject (Category) Very largeRelatively small Complex (thousands of categories) Simple (single category) Large prior to appear in an image Small prior Easy to collect (not easy to learn from examples) Hard to collect

All images Intuition  Denote H to be the acceptance region of a classifier. We propose to minimize the Pr(All images) ( Pr(bkg)) in H except for the object samples. Background Object class All images Background We have a prior on the distribution of all natural images H H Black H is better!

Image smoothness measure Lower probability Distribution of Natural Images – Boltzmann distribution In frequency domain:

Antiface Lower probability Ω d object images Acceptance region

Main Idea Claim: for random natural images viewed as unit vectors, is large on average. – for all positive class – d is smooth is large on average for random natural image. Anti-Face detector is defined as a vector d satisfying:

Discrimination SMALL LARGE If x is an image and  is a target class:

Cascade of Independent Detectors 7 inner products 4 inner products

PROJECT 2 Detect road signs in video 1)Use antiface method to learn a road sign under viewpoint variation 2)Use sign spatial location in the frame as an additional cue 3)Use scale change as an additional cue 4) Use evidence integration to combine evidence of sign presence in video stream.

Training with small number of examples Majority of object detection method require a large number of training examples. Goal: to design a classifier that can learn from a small number of examples Train existing classifiers on few examples Overfiting: learns by hart the training examples, performs poor on unseen examples.

Linear SVM Maximal margin Enough training data Class 1 Class 2 Not Enough training data

Linear SVM –Detection Task Class 1 Class 2

MM with prior Object class

Other Priors? Current prior uses the simplest features – DCT. These features are not robust to deformations. State-of-state of the art features – SIFT: local image features that are invariant to translation, rotation, scale. In addition, minor variations in illumination and viewpoint.

SIFT – Scale Invariant Feature Transform Descriptor overview: –Determine scale, local orientation as the dominant gradient direction. Use this scale and orientation to make all further computations invariant to scale and rotation. –Compute gradient orientation histograms of several small windows (128 values for each point) –Normalize the descriptor to make it invariant to intensity change David G. Lowe, "Distinctive image features from scale-invariant keypoints,“ International Journal of Computer Vision, 60, 2 (2004), pp

PROJECT 3 SIFT statistics: The goal of the project is to learn the statistics of state of the art features – SIFT to design a prior for recognition of images represented by SIFTs.

Patch-Based Face Representation Patched-based representation of a human face has several advantages – It can be used in privacy preserving applications where the identity of the person, specifically its photo is classified. –It can be used in face identification with occlusions, such as glasses, facial hair, etc. –Since local patches can be assumed planar, it can also remove the effect of illumination change.

Patch-Based Face Representation A face is represented by a collection of informative patches: Assume that the face is represented by N patches. Patch centers Patch size –could vary

Gallery Public database of faces – M faces 1 2 N

Indexing 14

… N 5 V= Resulting vector V could be used for face recognition, but the picture of the person is not saved, thus it cannot be misused.

Recognition Enrolled people V1 V2 … Vk … N 5 V = V is matched to each Vi (i=1..k) using Hamming Distance Can be done more robust – see project description

PROJECT 4 “Clusteron” This project investigates a new patched-based representation of a human face and applies it to face identification.

Lighting changes objects appearance.

Specular Lambertian How do we recognize these objects?

Few Definitions: Reflection Reflection - The scattering of light from an object. Two extreme cases: diffuse reflection and specular reflection. Real objects reflect light as a mixture of these two extremes.

Few Definitions: Lambertian Reflection Surface reflects equally in all directions. –Examples: chalk, clay, cloth, matte paint Brightness doesn’t depend on viewpoint. Amount of light striking surface proportional to cos θ. intensity albedo surface normal (light intensity)* (light direction)

Few Definitions: Specular Reflection Specular surfaces reflect light more strongly in some directions than in others. Appearance of a surface depends on the direction L of the light source, direction of the surface normal N, and direction V of viewing. The vectors L, N and R all lie in one plane

Few Definitions: Specular Reflection Perfect mirror: The angle of incidence equals the angle of reflection. rough specular R N L mirror R N L θθ Rough specular : Most specular surfaces reflect energy in a tight distribution (or lobe) centered on the optical reflection direction –Examples: metals,glass

N L llll R V rrrr Few Definitions: Phong Model Determine the angle α between the direction V of viewing and the direction R of reflection by an ideal mirror. Assume the intensity of reflected light is proportional to cos(α) The exponent n (“shine”) is determined empirically. Large values of n make the surface behave more like an ideal mirror.

Phong’s exponent controls how fast the highlight “falls-off”

Lambertian Main Approaches 2D methods based on quasi-invariance to lighting Model- based: 3D to 2D 3D image rendering Low dimensional representation of an object’s image set under different lightings compare

Main Approaches Specular 2D Methods: will be distracted by highlights and lack of real edges. 3D Methods: Specular objects cannot be well approximated by low- dimensional linear sub- spaces. Apply Lambertian methods and treat specularities as noise ?

Use specularities for recognition

Mapping image Gaussian sphere N L llll R V rrrr

Finding Specularity query map onto the sphere consistent specularity disk map back recovered highlights threshold specular candidates

Wrong Match query inconsistent map onto the sphere specularity disk map back recovered highlights threshold specular candidates

PROJECT 5 “Specularity detection” Assume that there are two types of points on a 3D sphere. A plane intersect a sphere in a disk. 1)Find a plane that separate points into two regions: a disk and the rest of the sphere with the minimal number of misclassification. (classification algorithm) 2)Test it on specularities obtained from images of real objects using mapping via 3D normals. (scan models using 3d scanner and take their pictures under different lighting directions).